Stock return prediction based on Bagging-decision tree

Wang, Huacheng; Jiang, Yanxia; Wang, Hui

doi:10.1109/gsis.2009.5408165

Cited by 13 publications

(6 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…From the methodology perspective, regression, neural networks, SVM, and decision tree are tools for stock market prediction [12], [28], [29]. With the success of deep learning in computer vision and Natural Language Processing tasks, there have been efforts on applying them to market and textual data (news and Tweets) to predict the stock market.…”

Section: Related Workmentioning

confidence: 99%

One Step Ahead: A Framework for Detecting Unexpected Incidents and Predicting the Stock Markets

Lyu

Zhang

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Unexpected incidents can be destructive or even disastrous, affecting the financial markets. Incidents such as the 9/11 attacks (2001), the Fukushima nuclear disaster (2011), and the COVID-19 outbreaks (2019, 2020) severely shocked both local and global markets. For investors, it is crucial to quantify the key facts that affect the incidents' impacts, and to estimate the reactions of the markets accurately and efficiently for global event-driven investment strategies. Though Web data and other alternative data allow such a possibility, it is still very challenging to mine noisy and often biased heterogeneous data sources, and construct a unified framework for modeling global markets across across time and regions. As a first attempt, we build a framework that extracts incident facts globally based on a deep neural network, feeds them into models built on a global event database complemented with novel socioeconomic datasets (e.g. nightlight data from satellites), and predicts stock market directions in a simulated real-world setting with interpretable results that outperform various baselines. Specifically, we study terrorist attacks in three countries for over 20 years on average, as a first effort to systematically quantify the impact on stock markets at a large scale using novel indicators. INDEX TERMS satellite data, stock market prediction, terrorist attacks, unexpected incidents

show abstract

Section: Related Workmentioning

confidence: 99%

One Step Ahead: A Framework for Detecting Unexpected Incidents and Predicting the Stock Markets

Lyu

Zhang

et al. 2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…To evaluate the effects of the individual elements, DL‐HPE model are compared with several reference models, in which conventional pruning criterions, that is, those proposed by Rooney et al and Ma et al, or conventional integration strategies, that is, equal weighting average and Bayesian committee machine, are embedded to the framework with the rest settings kept the same as DL‐HPE model. Moreover, two classical ensemble models, that is, bagging trees and boosting trees, are also adopted as reference models to show the integrated performance of DL‐HPE model. Their prediction results on the testing data are shown in Figure .…”

Section: Testing Of Uci Benchmark Datasetsmentioning

confidence: 99%

Prediction of liquid ammonia yield using a novel deep learning‐based heterogeneous pruning ensemble model

Dai

Yang

Zhang

et al. 2020

Asia-Pacific J Chem Eng

View full text Add to dashboard Cite

Liquid ammonia yield is the main index characterizing the process output of ammonia synthesis, the prediction of which is crucial for process control and optimization. However, the industrial process of ammonia synthesis involves multiple variables and strong nonlinearity, making it difficult to be accurately predicted using conventional mechanism‐driven model, or a certain type of data‐driven model. Therefore, a deep learning‐based heterogeneous pruning ensemble (DL‐HPE) model is proposed to overcome the limitations of conventional models. In this model, a “VDiv” pruning strategy that trades off diversity and accuracy is proposed and successfully applied to select the optimal subset from nine representative base models. Finally, the deep learning is employed to integrate the outputs of the involving models to generate the final prediction. The DL‐HPE method was applied to modeling the UCI standard dataset and the historical dataset collected from an ammonia plant in China. The results show that the method is superior to single model or other ensemble models both in accuracy and in robustness.

show abstract

“…Hickman (1958), was able to used times interest earned ratio and net profit ratio to predict the default rate on corporate bond. Wang, Jiang, and Wang (2009), employed the bagging-decision tree model to forecast stock returns by using fifty financial ratios on the financial data gathered. Gombola & Ketz (1983), studied cash flow statements and realized that profitability ratios ascertained from income statements was different from that which the cash flow provided.…”

Section: Literature Reviewmentioning

confidence: 99%

Evaluating the Stability of the Financial Ratios of Jordanian Industrial Companies

Rumman¹,

Kutum

2015

ijafr

View full text Add to dashboard Cite

The purpose of the study was to identify if the financial ratios of Jordanian industrial companies remained stable across sector and over time. The study used six financial ratios from fifty-six companies across six sectors with financial information from 2010 to 2014. A two way multivariate analysis of variance was performed to identify the stability of the ratios across the sectors and over the time. The results of the study showed that the financial ratios which showed some difference across sector were EBITTA (Earnings before Interest and Tax), CAT (Current Assets Turnover) and CFTA (Cash Flow to Total Assets). There were no differences observed between the financial ratios over time. The interaction of Time and Sector revealed no significant interaction effects. This suggests that as a whole, the financial ratios remained stable over time and sectors over the sectors and period chosen for the study.

show abstract

Stock return prediction based on Bagging-decision tree

Cited by 13 publications

References 24 publications

One Step Ahead: A Framework for Detecting Unexpected Incidents and Predicting the Stock Markets

One Step Ahead: A Framework for Detecting Unexpected Incidents and Predicting the Stock Markets

Prediction of liquid ammonia yield using a novel deep learning‐based heterogeneous pruning ensemble model

Evaluating the Stability of the Financial Ratios of Jordanian Industrial Companies

Contact Info

Product

Resources

About